DenoiseSplat: Feed-Forward Gaussian Splatting for Noisy 3D Scene Reconstruction
This addresses noise robustness in 3D reconstruction for applications like VR and robotics, but is incremental as it builds on existing Gaussian splatting methods.
The paper tackles 3D scene reconstruction from noisy multi-view images by proposing DenoiseSplat, a feed-forward Gaussian splatting method, and shows it outperforms baselines in PSNR/SSIM and LPIPS on a noisy benchmark.
3D scene reconstruction and novel-view synthesis are fundamental for VR, robotics, and content creation. However, most NeRF and 3D Gaussian Splatting pipelines assume clean inputs and degrade under real noise and artifacts. We therefore propose DenoiseSplat, a feed-forward 3D Gaussian splatting method for noisy multi-view images. We build a large-scale, scene-consistent noisy--clean benchmark on RE10K by injecting Gaussian, Poisson, speckle, and salt-and-pepper noise with controlled intensities. With a lightweight MVSplat-style feed-forward backbone, we train end-to-end using only clean 2D renderings as supervision and no 3D ground truth. On noisy RE10K, DenoiseSplat outperforms vanilla MVSplat and a strong two-stage baseline (IDF + MVSplat) in PSNR/SSIM and LPIPS across noise types and levels.